-
Notifications
You must be signed in to change notification settings - Fork 2.2k
Pull requests: ml-explore/mlx
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Use matrix kernels for global-scale gather_qqmm
#4481
opened Sep 8, 2026 by
dhiltgen
Contributor
Loading…
Add D256 to GQA-8 two-pass vector attention
#4477
opened Sep 8, 2026 by
wyanzhao
Contributor
Loading…
Use NAX attention for short causal D256 prefill
#4476
opened Sep 8, 2026 by
wyanzhao
Contributor
Loading…
Add type hints and docstrings for ALiBi layer
low priority
#4472
opened Sep 7, 2026 by
Ritabanm
Loading…
Refactor: Extract set_output Function from utils.h
low priority
#4467
opened Sep 5, 2026 by
JasonHonKL
Contributor
Loading…
Support uneven tensor parallel sharding in distributed linear layers
low priority
#4465
opened Sep 4, 2026 by
twallgren
Loading…
Win: Use DXGI for accurate WDDM VRAM memory budget
#4457
opened Sep 3, 2026 by
dhiltgen
Contributor
Loading…
Break the sibling cycle when an array is released by assignment
#4453
opened Sep 2, 2026 by
tudalex
Loading…
python: fix bytes() on non-contiguous arrays
await response
This pull request is waiting for response from the author.
low priority
#4449
opened Sep 1, 2026 by
axiom-of-choice
Contributor
Loading…
fix: keep single-element strided slice region round-tripping
await verification
This pull request is non-trivial and requires a human expert to verify its correctness.
low priority
#4446
opened Sep 1, 2026 by
axiom-of-choice
Contributor
•
Draft
Fix jaccl ring all_gather: direction 1 slice was not mirrored
await verification
This pull request is non-trivial and requires a human expert to verify its correctness.
low priority
#4443
opened Sep 1, 2026 by
Drifter4242
Loading…
Fix 32 bit dispatch grid overflow in Metal reductions
await verification
This pull request is non-trivial and requires a human expert to verify its correctness.
#4437
opened Aug 31, 2026 by
Lyxot
Contributor
Loading…
Small input linear and cubic upsampling should use dense matmuls
await verification
This pull request is non-trivial and requires a human expert to verify its correctness.
#4418
opened Aug 28, 2026 by
slink
Loading…
Pack eight value rows per SIMD-group in gated_delta_seq
#4409
opened Aug 26, 2026 by
wyanzhao
Contributor
Loading…
Add support for matrix transpose
await response
This pull request is waiting for response from the author.
low priority
#4402
opened Aug 25, 2026 by
aaishwarymishra
Contributor
Loading…
Clamp slice bounds in mixed fancy/slice indexing
await response
This pull request is waiting for response from the author.
low priority
#4397
opened Aug 25, 2026 by
Adityaj0
Contributor
Loading…
Add fused reduction support
await discussion
This pull request makes some major changes that requires the team to have a discussion.
await verification
This pull request is non-trivial and requires a human expert to verify its correctness.
enhancement
#4369
opened Aug 21, 2026 by
sakupan102
Loading…
Collapse the non sorted axes to pick the contiguous sort kernel
await verification
This pull request is non-trivial and requires a human expert to verify its correctness.
low priority
#4366
opened Aug 21, 2026 by
kapellirohith
Contributor
•
Draft
3 of 4 tasks
Add nanobind 3.0 split-mode support
await discussion
This pull request makes some major changes that requires the team to have a discussion.
#4359
opened Aug 19, 2026 by
XXXXRT666
Contributor
Loading…
4 tasks done
Previous Next
ProTip!
Updated in the last three days: updated:>2026-09-06.